Arthur Szlam (Facebook Research) - Language and Interaction in Minecraft
Language and Interaction in Minecraft
I will discuss a research program aimed at building a Minecraft assistant, in order to facilitate the study of agents that can complete tasks specified by dialogue, and eventually, to learn from dialogue interactions. I will describe the tools and platform we have built allowing players to interact with the agents and to record those interactions, and the data we have collected. In addition, I will describe an initial agent from which we (and hopefully others) can iterate.
Arthur Szlam
Arthur Szlam received his Ph.D. degree in computer science from Yale University, New Haven, Connecticut. He is a research scientist at Facebook AI Research, Menlo Park, California. Prior to joining Facebook, he was a postdoctoral fellow at the Institute for Mathematics and Its Applications at the University of Minnesota, Minneapolis, and the Institute for Pure and Applied Mathematics, University of California, Los Angeles, and an assistant professor at City College of New York. He is a Sloan Foundation fellow. His research interests are in computational harmonic analysis, the relationships between smoothness, frequency, and scale on graphs and data clouds, and applications to signal processing and machine learning.
